Michael Hyatt

NYT Bestselling Author | Speaker | Business Coach | AI Implementation Expert | Creator of Full Focus Planner | Orthodox Christian

[Michael Hyatt @MichaelHyatt]

How much time did you waste last week hunting for that one prompt that worked perfectly?

5 minutes? 10? 30?

Multiply that by 52 weeks.

Promptlee gives you those hours back.

Start free:
https://t.co/3T0IG2QWtl

[Michael Hyatt @MichaelHyatt]

@AlexFinn, do you have an opinion yet on the Hermes desktop app for Mac?

[GREG ISENBERG @gregisenberg]

Funny how the pendulum shifts

1. "GPT wrappers are worthless" → the value acrues to application layer

2. "AI will eliminate white collar jobs" → someone needs to manage all these AI agents and everyone is now saying white collar workers will rise due to AI

3. "Open source will never catch up" → Gemma and DeepSeek are good enough for 80% of tasks

4. "I only use Claude Code, Codex is mid" → Codex is becoming a super app. Coding, docs, browser, computer use, automations, all in one surface.

4. "You need to pick a model and go deep" → model loyalty is dead, the best founders swap weekly based on the task

5. "SaaS is dead" → This was mostly true but for some SaaS margins actually improve when agents pay for their own tokens and need their own seats

6. "AutoGPT is the future" → AutoGPT died. Then agents actually got good 2 years later with Hermes, OpenClaw, and managed agents. The idea was right. The timing was wrong.

7. "Prompt engineering is a career" → lasted about 18 months as a job title. Workflow engineering replaced it.

8. "Computer use is a gimmick" → "sent from computer use/ai agent will be the new sent from iphone

9. "AI design looks generic" → the generic look is a taste problem not a technology problem. The founders feeding their agents references from Japanese packaging, brutalist architecture, and 1960s print are getting beautiful output.

10. "Fine-tuning is the moat" → a well-structured Obsidian vault with good markdown files outperforms fine-tuning for most use cases and costs nothing.

11. "Benchmarks tell you which model to use" → benchmarks tell you which model won a test. I think we're all waking up to this lol.

12. "AI will consolidate into 2-3 winners" → AI is fragmenting into thousands of vertical applications built on commodity models. The consolidation is at the model layer. The explosion is at the application layer. Both are happening simultaneously.

13. "The hard part is building" → the hard part is choosing what to build. Building takes a weekend. Choosing the right thing to build takes taste, domain knowledge, and customer conversations. thats why i built https://t.co/a5ARFnvky2 to make it easier for you.

14. "The terminal is the future" → desktop apps just ate the terminal. Claude Code desktop, Codex app, both shipped GUI versions in the same month. The next 100 million agent users will never open a terminal (thank god).

I guarantee you I'm holding at least 2-3 beliefs right now that will look stupid by Christmas. I just don't know which ones. Neither do you. No one does. Build anyway.

Keep moving because this is the greatest time to be building.

I'm rooting for you.

[Peter H. Diamandis, MD @PeterDiamandis]

AI will democratize healthcare before it democratizes anything else. Why you ask? Because the stakes are the highest and the inefficiencies are the most ABSURD. Anyone that has been through the system knows this.

[Peter H. Diamandis, MD @PeterDiamandis]

The opposite of paranoia is pronoia, the irrational belief that the universe is conspiring in your favor. I have built my entire career on pronoia and I highly recommend it.

[Peter H. Diamandis, MD @PeterDiamandis]

AI is not coming for your job. AI is coming for the boring parts of your job. The parts you hate... The parts that drain you... If you let it take those, what remains is time for you to be CREATIVE.

[Michael Hyatt @MichaelHyatt]

@petercatkinson @claudeai Agreed. That’s why I have skills, knowledge, logs, and system files in Obsidian.

[Michael Hyatt @MichaelHyatt]

I've been all-in on @claudeai for the last six months. I love it. When it works.

However, for the last two months, I feel like I've been fighting it. Cowork Scheduled Tasks routinely break. It seems to take forever to generate output (switching from Opus 4.7 to Sonnet 4.6 helps some). Note: I'm on the $200 Max plan.

I started playing with @ChatGPT 5.5 a few weeks ago, mostly for Image 2.0. However, I've been pleasantly surprised by it’s text output, too.

It's much, much faster than Claude, and I've found the output to be excellent. No hallucinations so far.

Next, I want to test the writing output and compare it to Claude. I plan to give each platform the same assignment, using the same skill.

The jury's still out, but I think it's worth taking another look at @ChatGPT.

[Michael Hyatt @MichaelHyatt]

@_ReverseAI_ @almattydotcom @AlexFinn @Hermes_agentAI @gregisenberg @NetworkChuck Yes, but a local installation on a dedicated device is accessible via TailScale, no?

[Michael Hyatt @MichaelHyatt]

I’m about to install @Hermes_agentAI. Should I install on local, dedicated machine or VPS? Why?

cc: @gregisenberg, @AlexFinn, @NetworkChuck

[Michael Hyatt @MichaelHyatt]

@trey_smith @trey_smith, have you written anything on how it compares to OpenClaw, Hermes, and PaperClip?

[Michael Hyatt @MichaelHyatt]

If you’re wanting to move into creating AI agents, this advice is gold: “be the agent before you build the agent.”

[GREG ISENBERG @gregisenberg]

How to build a vertical AI agent cash-flowing startup:

find painful workflow in a boring industry → talk to 10 people who do that workflow every day → map every step, every tool, every spreadsheet, every phone call →

do the workflow manually first → be the agent before you build the agent → find the edge cases that break everything → document them in obsidian as structured markdown →

set up your agent stack → hermes for the harness → obsidian vault as the knowledge base → composio for authentication across apps → build your first 1-3 skills that solve the core pain →

use claude code or codex to build the product → use agents to set up other agents → use perplexity MCP and context7 for up-to-date docs → let the agent handle the scaffolding while you focus on the workflow logic →

ship the agent to your first 5 customers for free → watch what they actually use it for → they will surprise you → the thing you built for isn't always the thing they need most →

build content around the niche → not "building in public" content → useful content → the tips, the shortcuts, the pain points that only someone who does this workflow would know → become the person for that niche →

charge per outcome not per seat → per lease renewed, per claim processed, per candidate sourced → the ROI conversation takes 10 seconds when it's tied to a result →

set up watchdogs and alerts → your agent emails you when a cron job breaks or a skill fails → the customer should never have to tell you something is broken →

connect to open router → see exact costs per model per task → use GPT 5.5 for tool calls → use open source for lightweight tasks → route the right model to the right job → watch your margins double →

let hermes write to its own memory after every task → the agent compounds → the longer it runs the better it gets → that accumulated memory becomes your moat → a competitor can clone your product but they can't clone 6 months of context →

expand the workflow → you started with one step → add the next → then the next → now you own the entire workflow end to end → you went from a tool to the operating system for that vertical →

stack the agents → one agent is a side project → five agents across five customers is a business → each one runs in its own environment → you check in once a day →

raise only if you need capital not credibility → most agent businesses should never raise → the margins are too good to give away equity → stay lean → stay profitable → repeat

i'm rooting for you

[Michael Hyatt @MichaelHyatt]

@ElDeFiante @AlexFinn @Hermes_agentAI @gregisenberg @NetworkChuck No doubt. But it’s paid for.

[Michael Hyatt @MichaelHyatt]

@__axmi__ @Teknium @Hermes_agentAI @gregisenberg @AlexFinn @NetworkChuck I don’t.

[Michael Hyatt @MichaelHyatt]

@dsog @Teknium @Hermes_agentAI @gregisenberg @AlexFinn @NetworkChuck Then how do you learn? Geesh.

[Michael Hyatt @MichaelHyatt]

@__axmi__ @Teknium @Hermes_agentAI @gregisenberg @AlexFinn @NetworkChuck I do all that in Obsidian. Everything I do during the day is logged as I go. Each morning, I have Claude review the last 14-days worth of logs.

[Peter H. Diamandis, MD @PeterDiamandis]

I believe a 60 year old who masters AI tools will outperform a 25 year old who refuses to touch it. Age is not the variable. Willingness is.

[Michael Hyatt @MichaelHyatt]

@alejandroreyes @Paperclip_AI @NetworkChuck @AlexFinn @gregisenberg @dotta @IMJustinBrooke I’d love to see that. Is this the best video to watch?

https://t.co/LMPfNgGtKF

[Michael Hyatt @MichaelHyatt]

Now I’m thinking about jumping over Hermes and installing @Paperclip_AI. I can always use Hermes as an agent. I love the vision of AI orchestration at this level.

cc: @NetworkChuck, @AlexFinn, @gregisenberg, @dotta

[Michael Hyatt @MichaelHyatt]

@verncrawford @Paperclip_AI @NetworkChuck @AlexFinn @gregisenberg @dotta Yep. Got that.

[Michael Hyatt @MichaelHyatt]

@dalethomas50 @Slazerslaze @Paperclip_AI @NetworkChuck @AlexFinn @gregisenberg @dotta I’m hoping I can control that in the model selection. If there’s one thing I learned from my OpenClaw experiment, don’t use the Claude 4.7 API for everything!

[Michael Hyatt @MichaelHyatt]

@petercatkinson @Paperclip_AI @NetworkChuck @AlexFinn @gregisenberg @dotta For the sake of greater freedom. That’s the end-goal. AI is just a means to that end.

I wrote about it here: https://t.co/74t59CEPJd

[Michael Hyatt @MichaelHyatt]

@joelcomm @Paperclip_AI @NetworkChuck @AlexFinn @gregisenberg @dotta This: https://t.co/74t59CEPJd